A method and system for intelligent detection of faults in building electromechanical systems

Abstract

The present invention discloses a method and system for intelligent detection of mechanical and electrical system faults in a building. The present invention relates to the technical field of mechanical and electrical system maintenance in a building, and comprises the following steps: system data collection, health value assessment, fault prediction, maintenance priority, assessing the importance of mechanical and electrical equipment that needs maintenance through a priority scoring algorithm, obtaining a maintenance priority score S, notifying maintenance personnel to perform maintenance on the mechanical and electrical equipment in sequence according to the maintenance priority score S, and storing the data. The method is capable of quantifying the health value of the equipment through a mechanical and electrical system health assessment algorithm, predicting the risk of equipment failure in combination with a fault probability prediction algorithm, judging in advance whether the equipment needs maintenance, avoiding damage to the system caused by sudden failures, reducing downtime and maintenance costs, assessing the equipment maintenance priority through a priority scoring algorithm, reasonably allocating maintenance resources, improving maintenance efficiency, reducing excessive maintenance, and ensuring the effect of stable operation of the mechanical and electrical system.

Description

Technical Field

[0001] The present invention relates to the technical field of building electromechanical system maintenance, and in particular to a method and system for intelligent fault detection of a building electromechanical system. Background Art

[0002] Building electromechanical systems include air conditioning, lighting, power supply, water supply and drainage, fire protection and other systems, which are vital components of modern buildings. With the increasing number of buildings and the increasing complexity of building electromechanical systems, fault detection and diagnosis have become particularly important. In building electromechanical systems, a large number of electromechanical equipment, such as motor equipment, lighting equipment, water pump equipment and air conditioning equipment, are required to maintain the normal operation of building electromechanical systems, so fault diagnosis and maintenance of equipment in building electromechanical systems are very important.

[0003] At present, in terms of electromechanical system fault detection, manual detection is usually carried out when the electromechanical equipment cannot work normally, and then maintenance is carried out. That is, maintenance is carried out after the fault occurs, which may easily cause production interruption or equipment damage. In addition, the electromechanical equipment is maintained according to the order determined by humans, which leads to the equipment with serious problems not being maintained in time, while the minor equipment is over-maintained, resulting in a waste of maintenance resources and increased system downtime. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for intelligent detection of faults in a building electromechanical system, which solves the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for intelligent detection of faults in a building electromechanical system, comprising the following steps:

[0006] System data acquisition: install the sensor equipment at the monitoring position in the electromechanical system. The sensor equipment monitors the operating data of the electromechanical system in real time and transmits it to the central processor via wireless transmission;

[0007] Health value assessment: After the data is transmitted to the central processor, the electromechanical system health assessment algorithm is used to evaluate the state of the electromechanical system in combination with the electromechanical system operation data to obtain the electromechanical equipment health value H;

[0008] Fault prediction: After obtaining the health value H of the electromechanical equipment, the fault probability prediction algorithm is used to predict the fault probability of the electromechanical system, and the fault probability P(t) of the electromechanical equipment at the current time is obtained. The maintenance threshold of P(t) is set to Y. When P(t) is greater than Y, it means that the electromechanical equipment needs maintenance.

[0009] Maintenance priority: The importance of the electromechanical equipment that needs maintenance is evaluated through a priority scoring algorithm, and the maintenance priority score S is obtained by combining the health value H of the electromechanical equipment and the failure probability P(t) of the electromechanical equipment at the current time. The maintenance personnel are notified to maintain the electromechanical equipment in order according to the maintenance priority score S;

[0010] Data storage: store the operation data and environmental data of the electromechanical system, and record the maintenance data of each electromechanical equipment that needs maintenance for subsequent use.

[0011] Optionally, in the system data collection step, the wireless transmission method is a wifi module.

[0012] Optionally, the electromechanical system health assessment algorithm process is as follows:

[0013] ;

[0014] Where H is the health value of electromechanical equipment;

[0015] W i is the weight of the i-th sensor, ranging from 0.5 to 1;

[0016] D cur,i is the data value of the i-th sensor;

[0017] D max,i is the safety threshold of the i-th sensor;

[0018] n is the number of sensors;

[0019] is the fault frequency;

[0020] Where F is the number of failures in the most recent time period;

[0021] T is the length of the time period;

[0022] θ is the fault frequency influence coefficient, which takes the value of 1;

[0023] The health value H of the electromechanical equipment indicates the health status of the electromechanical equipment. The larger H is, the better the health status of the electromechanical equipment is, and vice versa. Displaying the health status of the electromechanical equipment in a quantitative form can help staff quickly understand the current operating status of the electromechanical system.

[0024] Optionally, the fault probability prediction algorithm process is as follows:

[0025] ;

[0026] Where P(t) is the failure probability of the electromechanical equipment at the current time;

[0027] x j is the operating status value of the electromechanical equipment at time j;

[0028] μ is the historical average normal state value of the electromechanical equipment, which is determined based on the mean of the long-term operation data of the electromechanical equipment and represents the normal operation state value of the electromechanical equipment without any faults;

[0029] t is the number of time points;

[0030] M is the time window size, indicating the length of historical data;

[0031] |x j -μ| is the degree to which the electromechanical equipment deviates from the normal operating state value, indicating the abnormal value of the working state of the electromechanical equipment;

[0032] is the outlier deviation square ratio, which amplifies the outlier impact, making larger outliers have a more significant impact on the failure probability;

[0033] P represents the failure probability of electromechanical equipment. The larger P(t) is, the greater the risk of failure probability of electromechanical equipment. The maintenance threshold of P(t) is set to Y, and the maintenance threshold Y is 0.1. When P(t) is greater than Y, it means that the electromechanical equipment needs maintenance. By setting the maintenance threshold Y, different electromechanical equipment in the electromechanical system can be divided into equipment that needs maintenance and equipment that does not need maintenance. When the electromechanical equipment is judged to need maintenance, the failure frequency influence coefficient θ in the electromechanical system health assessment algorithm will be reduced to reduce the health value of the electromechanical equipment. The change of θ is expressed as follows:

[0034] ;

[0035] Where P(t) is the failure probability of the electromechanical equipment at the current time;

[0036] K is the adjustment coefficient, which ranges from 0.6 to 1 and is used to represent the impact of the failure probability on the health value.

[0037] Optionally, the priority scoring algorithm process is as follows:

[0038] ;

[0039] Where S is the maintenance priority score;

[0040] P(t) is the failure probability of the electromechanical equipment at the current time;

[0041] α is the failure probability influence coefficient, ranging from 0 to 1;

[0042] H is the health value of electromechanical equipment;

[0043] β is the health value influence coefficient;

[0044] A is the use time of electromechanical equipment;

[0045] A max It is the design life of electromechanical equipment;

[0046] γ is the equipment life impact coefficient, ranging from 0 to 1;

[0047] The maintenance priority score S indicates the risk level of failure of the electromechanical equipment that needs maintenance. The larger the S is, the greater the risk of failure of the electromechanical equipment and the higher the importance of maintenance. The electromechanical equipment that needs maintenance is maintained according to the maintenance priority score S.

[0048] Optionally, the data storage step uses a combination of a cloud service platform and an entity storage, wherein the entity storage uses a mechanical hard disk, and the mechanical hard disk is used to regularly back up data.

[0049] Optionally, the cloud service platform includes a visualization tool for visualizing the stored data. Managers can log in to the cloud service platform through a terminal device and view the electromechanical system data.

[0050] The present application provides a building electromechanical system fault intelligent detection system, including a sensor module, a data transmission module, a central processing module and a data storage module;

[0051] The sensor module is used to monitor the operation data of each electromechanical device in the electromechanical system, and the data transmission module is used to transmit the operation data to the central processing module;

[0052] The central processing module includes a central processing unit for detecting and analyzing mechanical and electrical equipment faults based on operating data;

[0053] The data storage module is used to store the electromechanical system data for subsequent use.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] 1. The present invention analyzes the health status of electromechanical equipment through an electromechanical system health assessment algorithm in combination with operating data, and quantifies the results to obtain the health value of the electromechanical equipment, so that management personnel can quickly understand the performance degradation of the electromechanical equipment, and then use a fault probability prediction algorithm in combination with historical data for analysis to predict the failure probability of the electromechanical equipment, obtain the failure probability of the electromechanical equipment at the current time, and set a maintenance threshold for the failure probability of the electromechanical equipment at the current time. According to whether the result is greater than the maintenance threshold, it is judged that the electromechanical equipment needs maintenance, without waiting until the fault occurs, to prevent sudden equipment failure from causing harm to the system, thereby reducing system downtime and maintenance costs.

[0056] 2. The present invention evaluates the importance of electromechanical equipment that needs maintenance through a priority scoring algorithm. The priority scoring algorithm combines the health value of the electromechanical equipment and the failure probability of the electromechanical equipment at the current time and the factors affecting the equipment life, and adjusts each influencing factor according to the situation to obtain a maintenance priority score. The higher the maintenance priority score, the more serious the electromechanical equipment situation is and the higher the maintenance importance is. The electromechanical equipment is sorted according to the maintenance priority score, and then the staff maintains the electromechanical equipment in sequence according to the sorting, so as to reasonably allocate maintenance resources, avoid excessive maintenance, reduce system downtime, improve maintenance efficiency, and ensure the stability of the electromechanical system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a flow chart of the method of the present invention;

[0058] Figure 2 This is a block diagram of the system modules of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] For examples, see Figure 1 and Figure 2 , this implementation provides a building electromechanical system fault intelligent detection method, including the following steps:

[0061] System data acquisition: install sensor equipment at the monitoring position in the electromechanical system. The sensor equipment monitors the operation data and environmental data of the electromechanical system in real time and transmits it to the central processor via wireless transmission;

[0062] Health value assessment: After the data is transmitted to the central processor, the electromechanical system health assessment algorithm is used to evaluate the state of the electromechanical system in combination with the electromechanical system data to obtain the health value H of the electromechanical equipment. i ;

[0063] Fault prediction: After obtaining the health value H of the electromechanical equipment, the fault probability prediction algorithm is used to predict the fault probability of the electromechanical system, and the fault probability P(t) of the electromechanical equipment at the current time is obtained. The maintenance threshold of P(t) is set to Y. When P(t) is greater than Y, it means that the electromechanical equipment needs maintenance.

[0064] Maintenance priority: evaluate the importance of the electromechanical equipment that needs maintenance through the priority scoring algorithm, and combine the health value H of the electromechanical equipment and the failure probability P(t) of the electromechanical equipment at the current time to obtain the maintenance priority score S. According to the maintenance priority score S, the maintenance personnel are notified to maintain the electromechanical equipment;

[0065] Data storage: Stores the operating data and environmental data of the electromechanical system, and marks the cause of failure of each electromechanical equipment that requires maintenance for subsequent use.

[0066] In this embodiment, by installing sensor equipment in the electromechanical system, the operation data of the electromechanical equipment can be detected in real time without manual checking one by one, thereby improving the detection efficiency. Then, the health status of the electromechanical equipment is analyzed by the electromechanical system health assessment algorithm in combination with the operation data, and the results are quantified for easy understanding, so as to obtain the electromechanical equipment health value H. The higher the electromechanical equipment health value H, the better the electromechanical equipment status, and vice versa, so that the management personnel can quickly understand the operation status and performance degradation of the electromechanical system. Then, by using the fault probability prediction algorithm and combining with historical data for analysis, the fault probability of the electromechanical equipment is predicted to obtain the fault probability P(t) of the electromechanical equipment at the current time. The larger P(t) is, the higher the risk of failure of the electromechanical equipment is, and the maintenance threshold of P(t) is set to Y. When P(t) is greater than Y, it indicates that the electromechanical equipment needs maintenance, so as to decide to maintain the electromechanical equipment by the probability prediction method, without waiting until the failure occurs, in order to prevent the sudden failure of the equipment from causing harm to the system. The management personnel can take measures in advance to prevent the occurrence of failures and reduce system downtime and maintenance costs.

[0067] Finally, the importance of the electromechanical equipment that needs maintenance is evaluated through the priority scoring algorithm. The priority scoring algorithm combines the health value H of the electromechanical equipment and the failure probability P(t) of the electromechanical equipment at the current time, as well as the equipment life factor to obtain the maintenance priority score S. The higher the maintenance priority score S, the more serious the electromechanical equipment condition and the higher the maintenance importance. The electromechanical equipment is sorted according to the maintenance priority score S, and then the staff maintains the electromechanical equipment in turn, so as to reasonably allocate maintenance resources, avoid excessive maintenance, reduce system downtime, improve maintenance efficiency, and ensure the stability of the electromechanical system operation.

[0068] Furthermore, in the system data collection step, the wireless transmission method is a wifi module.

[0069] Specifically, since the electromechanical system includes a large number of electromechanical devices, a large amount of data transmission is required. The WiFi module has a high transmission rate and can quickly transmit a large amount of data, thereby ensuring the real-time transmission of electromechanical equipment detection data.

[0070] Furthermore, the electromechanical system health assessment algorithm process is as follows:

[0071] ;

[0072] Where H is the health value of electromechanical equipment;

[0073] W i is the weight of the i-th sensor, ranging from 0.5 to 1;

[0074] D cur,i is the data value of the i-th sensor;

[0075] D max,i is the safety threshold of the i-th sensor;

[0076] n is the number of sensors;

[0077] is the fault frequency;

[0078] Where F is the number of failures in the most recent time period;

[0079] T is the length of the time period;

[0080] θ is the fault frequency influence coefficient, which takes the value of 1;

[0081] Specifically, the detection of a certain electromechanical equipment in the electromechanical system may include multiple sensors. The electromechanical system health assessment algorithm integrates the data of multiple sensors and quantifies the results to obtain the electromechanical equipment health value H, which represents the health status of the electromechanical equipment. The larger H is, the better the health status of the electromechanical equipment is, and vice versa. The health status of the electromechanical equipment is displayed in real time in a quantitative form, which can help the staff quickly understand the current operating status of the electromechanical system. At the same time, the weight W of the i-th sensor can be adjusted according to different electromechanical equipment. i Adjustments should be made to make it applicable to different types of electromechanical equipment. For example, air-conditioning equipment should focus on air temperature, cooling water temperature, and indoor temperature data, while electrical equipment should focus on current, voltage and other data.

[0082] Furthermore, the fault probability prediction algorithm process is as follows:

[0083] ;

[0084] Where P(t) is the failure probability of the electromechanical equipment at the current time;

[0085] x j is the operating status value of the electromechanical equipment at time j;

[0086] μ is the historical average normal state value of the electromechanical equipment, which is determined based on the mean of the long-term operation data of the electromechanical equipment and represents the normal operation state value of the electromechanical equipment without any faults;

[0087] t is the number of time points;

[0088] M is the time window size, indicating the length of historical data;

[0089] |x j -μ| is the degree to which the electromechanical equipment deviates from the normal operating state value, indicating the abnormal value of the working state of the electromechanical equipment;

[0090] is the outlier deviation square ratio, which amplifies the outlier impact, making larger outliers have a more significant impact on the failure probability;

[0091] P represents the failure probability of electromechanical equipment. The larger P(t) is, the greater the risk of failure probability of electromechanical equipment. The maintenance threshold of P(t) is set to Y, and the maintenance threshold Y is 0.1. When P(t) is greater than Y, it means that the electromechanical equipment needs maintenance. By setting the maintenance threshold Y, different electromechanical equipment in the electromechanical system can be divided into equipment that needs maintenance and equipment that does not need maintenance. When the electromechanical equipment is judged to need maintenance, the failure frequency influence coefficient θ in the electromechanical system health assessment algorithm will be reduced to reduce the health value of the electromechanical equipment. The change of θ is expressed as follows:

[0092] ;

[0093] Where P(t) is the failure probability of the electromechanical equipment at the current time;

[0094] K is the adjustment coefficient, which ranges from 0.6 to 1 and is used to represent the impact of the failure probability on the health value.

[0095] Specifically, the decision to maintain electromechanical equipment is made through the probability prediction method, without waiting until a fault occurs, to prevent sudden equipment failure from causing harm to the system. Managers can take measures in advance to prevent the occurrence of faults, reduce system downtime and maintenance costs, and set the fault frequency influence coefficient θ to change when P(t) is greater than Y, so that the electromechanical system health assessment algorithm can be adjusted according to the actual situation, so as to be more accurate in subsequent fault detection and improve the accuracy of intelligent detection of building electromechanical system faults.

[0096] Furthermore, the priority scoring algorithm process is as follows:

[0097] ;

[0098] Where S is the maintenance priority score;

[0099] P(t) is the failure probability of the electromechanical equipment at the current time;

[0100] α is the failure probability influence coefficient, ranging from 0 to 1;

[0101] H is the health value of electromechanical equipment;

[0102] β is the health value influence coefficient, ranging from 0 to 1;

[0103] A is the use time of electromechanical equipment;

[0104] A max It is the design life of electromechanical equipment;

[0105] γ is the equipment life influence coefficient.

[0106] Specifically, the higher the maintenance priority score S, the greater the risk of mechanical and electrical equipment failure and the higher the importance of maintenance. The mechanical and electrical equipment is ranked according to the maintenance priority score S, and then the staff maintains the mechanical and electrical equipment in sequence according to the ranking, so as to reasonably allocate maintenance resources, avoid excessive maintenance, reduce system downtime, improve maintenance efficiency, and ensure the stability of the building's mechanical and electrical system operation.

[0107] Furthermore, in the data storage step, a combination of a cloud service platform and an entity storage is used, wherein the entity storage uses a mechanical hard disk, and the mechanical hard disk is used to back up data regularly.

[0108] Specifically, storing data through a combination of a cloud service platform and on-premises storage can avoid data loss and can flexibly expand storage capacity according to demand to meet the storage needs of large amounts of data in building mechanical and electrical systems.

[0109] Furthermore, the cloud service platform includes a visualization tool for visualizing the stored data. Managers can log in to the cloud service platform through terminal devices and view the electromechanical system data.

[0110] The present application provides a building electromechanical system fault intelligent detection system, including a sensor module, a data transmission module, a central processing module and a data storage module;

[0111] The sensor module is used to monitor the operating data of each electromechanical device in the electromechanical system, and the data transmission module includes a wifi module for transmitting the operating data to the central processing module;

[0112] The central processing module includes a central processing unit for detecting and analyzing mechanical and electrical equipment faults based on operating data;

[0113] The data storage module is used to store the electromechanical system data for subsequent use. The data storage module includes a cloud service platform and a local storage device.

[0114] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent detection of mechanical and electrical system faults in a building, characterized in that: The following steps are involved: Step S1: System data acquisition, installing the sensor device at the monitoring position in the electromechanical system, the sensor device monitors the operating data of the electromechanical system in real time, and transmits it to the central processor via wireless transmission; Step S2: Health value evaluation: after the data is transmitted to the central processor, the state of the electromechanical system is evaluated using the electromechanical system health evaluation algorithm and combined with the electromechanical system operation data to obtain the electromechanical equipment health value H; Step S3: Fault prediction: after obtaining the health value H of the electromechanical equipment, the fault probability prediction algorithm is used to predict the fault probability of the electromechanical system, and the fault probability P(t) of the electromechanical equipment at the current time is obtained. The maintenance threshold of P(t) is set to Y. When P(t) is greater than Y, it indicates that the electromechanical equipment needs maintenance. Step S4: Maintenance priority: evaluate the importance of the electromechanical equipment that needs maintenance through the priority scoring algorithm, and combine the health value H of the electromechanical equipment and the failure probability P(t) of the electromechanical equipment at the current time to obtain the maintenance priority score S. Notify the maintenance personnel to maintain the electromechanical equipment in turn according to the maintenance priority score S; Step S5: Data storage, storing the operation data and environmental data of the electromechanical system, and recording the maintenance data of each electromechanical equipment that needs maintenance; The electromechanical system health assessment algorithm process is as follows: ； Where H is the health value of electromechanical equipment; W i is the weight of the i-th sensor, ranging from 0.5 to 1; D cur,i is the data value of the i-th sensor; D max,i is the safety threshold of the i-th sensor; n is the number of sensors; is the fault frequency; Where F is the number of failures in the most recent time period; T is the length of the time period; θ is the fault frequency influence coefficient; The health value H of the electromechanical equipment indicates the health status of the electromechanical equipment. The larger H is, the better the health status of the electromechanical equipment is, and vice versa. Displaying the health status of the electromechanical equipment in a quantitative form can help staff quickly understand the current operating status of the electromechanical system.

2. The intelligent detection method for building electromechanical system faults according to claim 1 is characterized in that: In the system data collection step, the wireless transmission method is a wifi module.

3. The intelligent detection method for building electromechanical system faults according to claim 2 is characterized in that: The fault probability prediction algorithm process is as follows: ； Where P(t) is the failure probability of the electromechanical equipment at the current time; x j is the operating status value of the electromechanical equipment at time j; μ is the historical average normal state value of the electromechanical equipment, which is determined based on the mean of the long-term operation data of the electromechanical equipment and represents the normal operation state value of the electromechanical equipment without any faults; t is the number of time points; M is the time window size, indicating the length of historical data; |x j -μ| is the degree to which the electromechanical equipment deviates from the normal operating state value, indicating the abnormal value of the working state of the electromechanical equipment; is the outlier deviation square ratio, which amplifies the outlier impact, making larger outliers have a more significant impact on the failure probability; P represents the failure probability of electromechanical equipment. The larger P(t) is, the greater the risk of failure probability of electromechanical equipment. The maintenance threshold of P(t) is set to Y, and the maintenance threshold Y is 0.

1. When P(t) is greater than Y, it means that the electromechanical equipment needs maintenance. By setting the maintenance threshold Y, different electromechanical equipment in the electromechanical system can be divided into equipment that needs maintenance and equipment that does not need maintenance. When the electromechanical equipment is judged to need maintenance, the failure frequency influence coefficient θ in the electromechanical system health assessment algorithm will be reduced to reduce the health value of the electromechanical equipment. The change of θ is expressed as follows: ； Where P(t) is the failure probability of the electromechanical equipment at the current time; K is the adjustment coefficient, which ranges from 0.6 to 1 and is used to represent the impact of the failure probability on the health value.

4. The intelligent detection method for building electromechanical system faults according to claim 3 is characterized in that: The priority scoring algorithm process is as follows: ； Where S is the maintenance priority score; P(t) is the failure probability of the electromechanical equipment at the current time; α is the failure probability influence coefficient, ranging from 0 to 1; H is the health value of electromechanical equipment; β is the health value influence coefficient; A is the use time of electromechanical equipment; A max It is the design life of electromechanical equipment; γ is the equipment life impact coefficient, ranging from 0 to 1; The maintenance priority score S indicates the risk level of failure of the electromechanical equipment that needs maintenance. The larger the S is, the greater the risk of failure of the electromechanical equipment and the higher the importance of maintenance. The electromechanical equipment that needs maintenance is maintained according to the maintenance priority score S.

5. The intelligent fault detection method for building electromechanical system according to claim 4 is characterized in that: The data storage step uses a combination of a cloud service platform and an on-body storage, wherein the on-body storage uses a mechanical hard disk, and the mechanical hard disk is used to back up data regularly.

6. The intelligent fault detection method for building electromechanical system according to claim 5 is characterized in that: The cloud service platform includes a visualization tool for visualizing the stored data. Managers can log in to the cloud service platform through terminal devices and view the electromechanical system data.

7. The detection system used in the intelligent detection method for building electromechanical system faults according to claim 1 is characterized in that: It includes a sensor module, a data transmission module, a central processing module and a data storage module; The sensor module is used to monitor the operation data of each electromechanical device in the electromechanical system, and the data transmission module is used to transmit the operation data to the central processing module; The central processing module includes a central processing unit for detecting and analyzing mechanical and electrical equipment faults based on operating data; The data storage module is used to store electromechanical system data.

Images